Autonomous Frontend Browser Tools MCP Server
@winds-ai/autonomous-frontend-browser-tools
npm
v1.4.20
Published by @winds-ai — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Autonomous Frontend Browser Tools — npx setup UI, connector server, Chrome extension, MCP server bin
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 7 = 87. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 9
high Shell/command execution in server code (browser-tools-server/dist/screenshot-service.js)MTC-SRC-002
In the server's implementation (`browser-tools-server/dist/screenshot-service.js:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ; import { exec } from "child_process"; import { fileURLToPath } from "url"; import { getScreenshotStoragePath, getDefau
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server browser-tools-server/dist/screenshot-service.js
medium Hardcoded egress to an external endpoint (browser-tools-mcp/dist/mcp-server.js)MTC-SRC-003
In the server's implementation (`browser-tools-mcp/dist/mcp-server.js:278`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch(`http://${host}:${port}/.identity`, { signal: AbortSignal.timeout(1000
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server browser-tools-mcp/dist/mcp-server.js
medium Hardcoded egress to an external endpoint (chrome-extension/background.js)MTC-SRC-003
In the server's implementation (`chrome-extension/background.js:684`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch(`http://${host}:${port}/.identity`, { signal: AbortSignal.timeout(3000), // 3 second
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server chrome-extension/background.js
medium Hardcoded egress to an external endpoint (chrome-extension/devtools.js)MTC-SRC-003
In the server's implementation (`chrome-extension/devtools.js:365`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch( `http://${settings.serverHost}:${settings.serverPort}/.identity`, { s
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server chrome-extension/devtools.js
medium Hardcoded egress to an external endpoint (chrome-extension/panel.js)MTC-SRC-003
In the server's implementation (`chrome-extension/panel.js:496`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch(`http://${host}:${port}/.identity`, { signal: AbortSignal.timeout(5000), // 5 second
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server chrome-extension/panel.js
medium Untrusted input concatenated into a command sink (browser-tools-server/dist/screenshot-service.js)MTC-SRC-009
In the server's implementation (`browser-tools-server/dist/screenshot-service.js:363`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eject) => { exec(`osascript -e '${appleScript}'`, (error, stdout, stderr) => { if (error) {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server browser-tools-server/dist/screenshot-service.js
low Shell/command execution in packaging/dev tooling (tools/afbt-entry.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/afbt-entry.js:12`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } = require("child_process"); function isInteractive() { return process.stdin.isTTY && process.stdout.isTT
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/afbt-entry.js
low Shell/command execution in packaging/dev tooling (tools/afbt-mcp.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/afbt-mcp.js:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: spawnSync } = require("child_process"); const entry = path.resolve(__dirname, "./afbt-entry.js"); const result = spawn
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/afbt-mcp.js
low Shell/command execution in packaging/dev tooling (tools/afbt-setup.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tools/afbt-setup.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: pawn, exec } = require("child_process"); const path = require("path"); const { join, resolve } = path; const fs = requir
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tools/afbt-setup.js
Tools 9
Each tool and what it can reach — statically extracted from the published source.
api.listTagsno sensitive capabilityapi.requestno sensitive capabilityapi.searchEndpointsno sensitive capabilitybrowser.console.readno sensitive capabilitybrowser.navigateno sensitive capabilitybrowser.network.inspectno sensitive capabilitybrowser.screenshotno sensitive capabilityui.inspectElementno sensitive capabilityui.interactno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (9 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.4.20 latest |
B 87/100 | 9 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @winds-ai/autonomous-frontend-browser-tools --onlineMore in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand